Overview

This 5 day course introduces academics and professional data analysts to Bayesian inference, using the Stan interface in R.

The atmosphere of the workshop will be friendly and supportive, with the goal of teaching the basics of Bayesian inference in Stan for academics and professionals alike from diverse backgrounds ranging from industry to research fields such as population health, social sciences, disaster risk reduction, and many more.

We will show participants how one can develop and compile Stan scripts for Bayesian inference through RStudio to perform basic parameter estimation, as well as a wide range of regression-based techniques from the simplest univariate linear models to more advanced multivariate spatial risk models.

Participants will leave the course with a clear understanding of the Bayesian approach to data analysis and inference, and its applications in a range of fields.

Who this course is for

The course is aimed at anyone who wants to develop an understanding of Bayesian methods, whether in academia or professional research settings.

Participants must be familiar with statistics up to and including multiple linear regression. Some prior experience of using R software is also necessary.

Course content

The course will be structured as follows:

• Day 1: Introduction to Probability Distributions
• Day 2: Introduction to Bayesian Inference
• Day 3: Bayesian Generalised Linear Models
• Day 4: Bayesian Hierarchical Regression Models
• Day 5: Spatial Conditional Autoregression Models

Teaching and structure

The course will consist of 5 lectures and 5 computer seminar sessions supported with live walkthrough coding demonstrations

Participants may wish to refresh their knowledge of basic statistics/regression and R coding prior to the course.

Certificates

Participants will be issued with a certificate of participation upon completion of the course.

Learning outcomes 

By the end of this course you will:

• Have both a foundational and advanced understanding of key principles of statistical modelling within a Bayesian framework
• Be able to perform inferential statistics on spatial and non-spatial data to carry out hypothesis testing for evidence-based research using the diverse types of regression-based models from a Bayesian framework
• Be able to perform spatial risk prediction for areal data as well as quantify levels of uncertainty using exceedance probabilities
• Have acquired new programming language skills in Stan (interfaced with RStudio).

Cost

The standard course fee is £500.

Course team

Dr. Anwar Musah

Anwar is a Lecturer in Social and Geographic Data Science in the UCL Department of Geography.

He is an experienced teacher of statistics and data science at UCL, from beginner to advanced levels. He has a particular interest in teaching Bayesian methods, having delivered training courses on it before. His research applies a range of advanced quantitative methods to topics in epidemiology, disaster risk reduction and the broader social sciences, mostly in global south contexts. 

Course information last modified: 26 Mar 2024, 16:10